Shenzhen Malong Technologies Co., Ltd.

Other

Dinglong Huang

Matthew Robert Scott

Weilin Huang

Sheng Guo

Haozhi Zhang

Kai Fu

Le Yin

Chenfan Zhuang

Dengke Dong

Methods and systems for training machine vision models (MVMs) with 'noisy' training datasets are described. A noisy set of images is received, where labels for some of the images are 'noisy' and/or incorrect. A progressively-sequenced learning curriculum is designed for the noisy dataset, where the images that are easiest to learn machine-vision knowledge from are sequenced near the beginning of the curriculum and images that are harder to learn machine-vision knowledge from are sequenced later in the curriculum. An MVM is trained via providing the sequenced curriculum to a supervised learning method, so that the MVM learns from the easiest examples first and the harder training examples later, i.e., the MVM progressively accumulates knowledge from simplest to most complex. To sequence the curriculum, the training images are embedded in a feature space and the &#x201c;complexity&#x201d; of each image is determined via density distributions and clusters in the feature space.

Complexity-based progressive training for machine vision models

Aspects of this disclosure include technologies for detecting mislabeled products. In one embodiment, the disclosed system will capture an image of a product when the MRL of the product is scanned or being scanned. After recognizing the product in the image, the size of the area containing the product may be calculated. Subsequently, the disclosed system can determine whether the MRL mismatches the product in the image if this size of the area containing the product does not match the standard size associated with the MRL.

Mislabeled product detection

Provided are a method and apparatus for identifying a product. The method includes: acquiring an image of the product; performing multilevel detection on the image to determine a label region of the product, specifically, an image region corresponding to a previous level of detection is greater than an image region corresponding to a following level of detection; and identifying information in the label region to determine information of the product. A product can be identified automatically by acquiring the image of the product and performing multilevel detection on the image, thereby efficiency is improved, a large number of products can be handled, and cost is reduced.

Method and apparatus for identifying a product

Provided are a self-service method and device. The method includes: acquiring by a camera video data associated with a shopping cart at a distance from a shelf less than a preset value; determining whether an article is being placed into the shopping cart, based on identification of the video data; if yes, acquiring an ID of the shopping cart, determining the placed article and associating the ID with the article; displaying a total sum of all articles associated with the ID to the user when detecting the shopping cart corresponding to the ID is located in a preset payment area in the shopping mall; and executing a permitting procedure for allowing the shopping cart corresponding to the ID to pass upon reception of a message fed back from the payment area and indicating that the total sum corresponding to the ID has been cleared.

Growing community of inventors

Shenzhen, China

Dinglong Huang